Chat

In this example, we will download a model and get a reply to a specific list of messages.

Python
Swift
TypeScript
Rust

Create a new project

uv init demo && cd demo

Install dependencies

uv add uzu

Paste into main.py

import asyncio

from uzu import (
    ChatConfig,
    ChatMessage,
    ChatReplyConfig,
    ChatSessionStreamChunk,
    Engine,
    EngineConfig,
)


async def main() -> None:
    engine_config = EngineConfig.create()
    engine = await Engine.create(engine_config)

    model = await engine.model("Qwen/Qwen3-0.6B")
    if model is None:
        raise RuntimeError("Model not found")
    async for update in (await engine.download(model)).iterator():
        print(f"Download progress: {update.progress}")

    messages = [
        ChatMessage.system().with_text("You are a helpful assistant"),
        ChatMessage.user().with_text("Tell me a short, funny story about a robot"),
    ]
    session = await engine.chat(model, ChatConfig.create())
    stream = await session.reply_with_stream(messages, ChatReplyConfig.create())
    message: ChatMessage | None = None
    async for chunk in stream.iterator():
        if isinstance(chunk, ChatSessionStreamChunk.Replies):
            replies = chunk.replies
            if replies:
                reply = replies[0]
                message = reply.message
                print(f"Generated tokens: {reply.stats.tokens_count_output}")
        elif isinstance(chunk, ChatSessionStreamChunk.Error):
            print(f"Error: {chunk.error}")
    if message is not None:
        print(f"Reasoning: {message.reasoning}")
        print(f"Text: {message.text}")


if __name__ == "__main__":
    asyncio.run(main())

Run the snippet

uv run main.py

Create a new SwiftUI project

Add the SDK

Add this package through SPM:

https://github.com/trymirai/uzu.git

Paste the snippet

import Uzu

public func runChat() async throws {
    let engineConfig = EngineConfig.create()
    let engine = try await Engine.create(config: engineConfig)
    
    guard let model = try await engine.model(identifier: "Qwen/Qwen3-0.6B") else {
        return
    }
    for try await update in try await engine.download(model: model).iterator() {
        print("Download progress: \(update.progress())")
    }
    
    let messages = [
        ChatMessage.system().withText(text: "You are a helpful assistant"),
        ChatMessage.user().withText(text: "Tell me a short, funny story about a robot")
    ]
    let session = try await engine.chat(model: model, config: .create())
    let stream = await session.replyWithStream(input: messages, config: .create())
    var message: ChatMessage? = nil
    for try await update in stream.iterator() {
        switch update {
        case .replies(let replies):
            let reply = replies.last
            message = reply?.message
            print("Generated tokens: \(reply?.stats.tokensCountOutput ?? 0)")
        case .error(let error):
            print("Error: \(error)")
        }
    }
    print("Reasoning: \(message?.reasoning() ?? "empty")")
    print("Text: \(message?.text() ?? "empty")")
}

Add the snippet call

var body: some View {
    VStack {
        Text("On-device AI")
    }
    .onAppear() {
        Task {
            try await runExampleName()
        }
    }
}

Make a new project folder

mkdir demo && cd demo

Initialize with pnpm

pnpm init

Install dependencies

pnpm add typescript ts-node @types/node -D
pnpm add @trymirai/uzu

Initialize a tsconfig.json

{
    "compilerOptions": {
        "target": "es2020",
        "module": "commonjs",
        "moduleResolution": "node",
        "strict": true,
        "esModuleInterop": true,
        "outDir": "dist",
        "types": [
            "node"
        ]
    },
    "include": [
        "*.ts"
    ]
}

Create main.ts

import { ChatConfig, ChatMessage, ChatReplyConfig, ChatSessionStreamChunkError, ChatSessionStreamChunkReplies, Engine, EngineConfig } from '@trymirai/uzu';

async function main() {
    let engineConfig = EngineConfig.create();
    let engine = await Engine.create(engineConfig);

    let model = await engine.model('Qwen/Qwen3-0.6B');
    if (!model) {
        throw new Error('Model not found');
    }
    for await (const update of await engine.download(model)) {
        console.log('Download progress:', update.progress);
    }

    let messages = [
        ChatMessage.system().withText('You are a helpful assistant'),
        ChatMessage.user().withText('Tell me a short, funny story about a robot')
    ];
    let session = await engine.chat(model, ChatConfig.create());
    let stream = await session.replyWithStream(messages, ChatReplyConfig.create());
    let message: ChatMessage | undefined;
    for await (const chunk of stream) {
        if (chunk instanceof ChatSessionStreamChunkReplies) {
            message = chunk.replies[0]?.message;
            console.log('Generated tokens: ', chunk.replies[0]?.stats.tokensCountOutput);
        } else if (chunk instanceof ChatSessionStreamChunkError) {
            console.error('Error: ', chunk.error);
        }
    }
    console.log('Reasoning: ', message?.reasoning);
    console.log('Text: ', message?.text);
}

main().catch((error) => {
    console.error(error);
});

Run the snippet

pnpm ts-node main.ts

Create a new project

cargo new demo && cd demo

Install dependencies

cargo add uzu --git https://github.com/trymirai/uzu
cargo add tokio --features full

Paste into src/main.rs

use uzu::{
    engine::{Engine, EngineConfig},
    session::chat::ChatSessionStreamChunk,
    types::session::chat::{ChatConfig, ChatMessage, ChatReplyConfig},
};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let engine_config = EngineConfig::default();
    let engine = Engine::new(engine_config).await?;

    let model = engine.model("Qwen/Qwen3-0.6B".to_string()).await?.ok_or("Model not found")?;
    let downloader = engine.download(&model).await?;
    while let Some(update) = downloader.next().await {
        println!("Download progress: {}", update.progress());
    }

    let messages = vec![
        ChatMessage::system().with_text("You are a helpful assistant".to_string()),
        ChatMessage::user().with_text("Tell me a short, funny story about a robot".to_string()),
    ];
    let session = engine.chat(model, ChatConfig::default()).await?;
    let stream = session.reply_with_stream(messages, ChatReplyConfig::default()).await;
    let mut last_message: Option<ChatMessage> = None;
    while let Some(chunk) = stream.next().await {
        match chunk {
            ChatSessionStreamChunk::Replies {
                replies,
            } => {
                if let Some(reply) = replies.first() {
                    last_message = Some(reply.message.clone());
                    println!("Generated tokens: {}", reply.stats.tokens_count_output.unwrap_or_default());
                }
            },
            ChatSessionStreamChunk::Error {
                error,
            } => {
                println!("Error: {error}");
            },
        }
    }
    if let Some(message) = last_message {
        println!("Reasoning: {}", message.reasoning().unwrap_or_default());
        println!("Text: {}", message.text().unwrap_or_default());
    }

    Ok(())
}

Run the snippet

cargo run --release

Once loaded, the same ChatSession can be reused for multiple requests until you drop it. Each model may consume a significant amount of RAM, so it’s important to keep only one session loaded at a time. For iOS apps, we recommend adding the Increased Memory Capability entitlement to ensure your app can allocate the required memory.

Overview

Quick start